EmptyDroplets (FDR <= 0.1) setwd("/media/jacopo/Elements/re_align/MM/PRJNA694128/25183/SAMN17249432/")
# Load the libraries (from Sarah script + biomart)
library(tidyverse) # packages for data wrangling, visualization etc
library(Seurat) # scRNA-Seq analysis package
library(clustree) # plot of clustering tree
library(ggsignif) # Enrich your 'ggplots' with group-wise comparisons
library(clusterProfiler) #The package implements methods to analyze and visualize functional profiles of gene and gene clusters.
library(org.Hs.eg.db) # Human annotation package neede for clusterProfiler
library(ggrepel) # extra geoms for ggplo2
library(patchwork) #multiplots
library(reticulate)
Load and do the QC for the cellranger data
#list.files(".")
dat <- Read10X(data.dir ="./out/counts_filtered/")
dat <- CreateSeuratObject(dat) # Create the seurat object from the 10x data
kb.initial <- dat@assays[["RNA"]]@counts@Dim[[2]]
cat("Initial number of cells:", kb.initial,
"\nNumber of genes:", dat@assays[["RNA"]]@counts@Dim[[1]])
## Initial number of cells: 9954
## Number of genes: 36601
Empty cells were already filtered, check for % mt RNA and death markers:
# first calculate the mitochondrial percentage for each cell
dat$percent_mt <- PercentageFeatureSet(dat, pattern="^MT.")
# make violin plots
mt_rna = 5
max_counts = 40000
# Check some feature-feature relationships
# % mt RNA vs n Counts, n Features vs n Counts
# Check some feature-feature relationships
# % mt RNA vs n Counts, n Features vs n Counts
VlnPlot(dat, features = c("nCount_RNA", "nFeature_RNA", "percent_mt")) + geom_hline(yintercept=mt_rna, linetype = "dotted")
plot1 <- FeatureScatter(dat, feature1 = "nCount_RNA", feature2 = "percent_mt")
plot1 <- plot1 + geom_hline(yintercept=mt_rna, linetype = "dotted")
plot2 <- FeatureScatter(dat, feature1 = "nCount_RNA", feature2 = "nFeature_RNA")
plot2 <- plot2 + geom_vline(xintercept = max_counts, linetype = "dotted")
plot1
plot2
## cells retained by mt RNA content ( 5 %): 5286
## percentage of retained cells: 53.1 %
## cells retained by counts ( 40000 ): 5252
## percentage of retained cells: 52.76 %
Check the distribution of the cells with low counts and control death markers:
min_counts = 300
hist(dat@meta.data$nCount_RNA, breaks = 100, xlab = "Counts")
hist(dat@meta.data$nCount_RNA, breaks = 500, xlab = "Counts", xlim = c(0,5000))
hist(dat@meta.data$nCount_RNA, breaks = 10000, xlab = "Counts", xlim = c(0,1000))
abline(v=min_counts, col="red", lty = 3)
The evident peak of cells with < 200 counts could contain dying
cells.
# Subset the dataset to focus only on those cells with low counts
dat.lowcount <- subset(dat, subset = nCount_RNA < min_counts)
# Get the mean of the counts for each gene and sort them decreasing
meanCounts <- rowMeans(GetAssayData(object = dat.lowcount, slot = 'counts'))
meanCounts <- sort(meanCounts, decreasing = T)
# A boxplot can help to observe the distribution of the means
#boxplot(meanCounts)
# Print the most highly expressed genes
head(meanCounts, 30)
## IGKC IGHA1 MALAT1 B2M SSR4 RPL10 FTL
## 34.4341880 19.5367521 3.2478632 2.3264957 1.0666667 1.0581197 0.7504274
## RPLP1 IGLC1 RPS27 RPS18 EEF1A1 RPL41 JCHAIN
## 0.6205128 0.6051282 0.5982906 0.5931624 0.5829060 0.5589744 0.5504274
## MZB1 TMSB10 RPS14 RPL13 HLA-C RPS19 RPL13A
## 0.4239316 0.4034188 0.3931624 0.3829060 0.3589744 0.3555556 0.3555556
## RPS27A RPL17 RPS6 RPL21 RPL35 HLA-B IGLC2
## 0.3470085 0.3401709 0.3350427 0.3316239 0.3282051 0.3196581 0.3145299
## JUNB MT-ND4
## 0.3042735 0.3042735
## cells retained by counts ( 300 ): 4667
## percentage of retained cells: 46.89 %
dir.create("result")
#saveRDS(dat, file = "./result/SAMN17249432_clean_QC.Rds")
#Normalize
dat <- NormalizeData(dat)
# Find the first 4000 variabe features
dat <- FindVariableFeatures(dat, selection.method = "vst", nfeatures = 4000)
Set mean expression to 0 and variance across 1 to avoid highly expressed genes drive the forwarding analyses. Since negative expression is meaningless, scaled data are useful only for UMAP and clustering
# scale data, the scaled data are saved in:
# dat[["RNA"]]@scale.data
all.genes <- rownames(dat)
dat <- ScaleData(dat, vars.to.regress = c("percent_mt","nCount_RNA"))
dat <- RunPCA(dat, features = VariableFeatures(object = dat), verbose = F, seed.use = 1)
#print(dat[["pca"]], dims = 1:5, nfeatures = 5)
UMAP is a graph-based method of clustering. The first step in this process is to construct a KNN graph based on the euclidean distance in PCA space:
dat <- FindNeighbors(dat, dims = 1:20)
The graph now can be used as input for the function
runUMAP()
dat <- RunUMAP(dat, dims = 1:20, seed.use = 1)
DimPlot(dat, reduction = 'umap', seed = 1)
## QC metrics
## markers